intent taxonomy with five visual intents characterized by participants' gaze behaviors.We demonstrated the difference between low vision and sighted participants' gaze behaviors and how visual ability affected low vision participants' gaze patterns across visual intents.Our findings underscore the importance of combining visual ability information, visual context, and eye tracking data in visual intent recognition, setting up a foundation for intent-aware assistive technologies for low vision people.

Obsessive-compulsive disorder (OCD) is a mental health condition that significantly impacts people's quality of life.While evidencebased therapies such as exposure and response prevention (ERP) can be effective, managing OCD symptoms in everyday life-an essential part of treatment and independent living-remains challenging due to fear confrontation and lack of appropriate support.To better understand the challenges and needs in OCD self-management, we conducted interviews with 10 participants with diverse OCD conditions and seven therapists specializing in OCD treatment.Through these interviews, we explored the characteristics of participants' triggers and how they shaped their compulsions, and uncovered key coping strategies across different stages of OCD episodes.Our findings highlight critical gaps between OCD self-management needs and currently available support.Building on these insights, we propose design opportunities for just-in-time self-management technologies for OCD, including personalized symptom tracking, just-in-time interventions, and support for OCD-specific privacy and social needs-through technology and beyond.

Reading is a challenging task for low vision people. While conventional low vision aids (e.g., magnification) offer certain support, they cannot fully address the difficulties faced by low vision users, such as locating the next line and distinguishing similar words. To fill this gap, we present GazePrompt, a gaze-aware reading aid that provides timely and targeted visual and audio augmentations based on users’ gaze behaviors. GazePrompt includes two key features: (1) a Line-Switching support that highlights the line a reader intends to read; and (2) a Difficult-Word support that magnifies or reads aloud a word that the reader hesitates with. Through a study with 13 low vision participants who performed well-controlled reading-aloud tasks with and without GazePrompt, we found that GazePrompt significantly reduced participants’ line switching time, reduced word recognition errors, and improved their subjective reading experiences. A follow-up silent-reading study showed that GazePrompt can enhance users’ concentration and perceived comprehension of the reading contents. We further derive design considerations for future gaze-based low vision aids.

Cooking is a vital yet challenging activity for blind and low vision (BLV) people, which involves many visual tasks that can be difficult and dangerous. BLV training services, such as vision rehabilitation, can effectively improve BLV people’s independence and quality of life in daily tasks, such as cooking. However, there is a lack of understanding on the practices employed by the training professionals and the barriers faced by BLV people in such training. To fill the gap, we interviewed six professionals to explore their training strategies and technology recommendations for BLV clients in cooking activities. Our findings revealed the fundamental principles, practices, and barriers in current BLV training services, identifying the gaps between training and reality.

While being able to read with screen magnifiers, low vision people have slow and unpleasant reading experiences. Eye tracking has the potential to improve their experience by recognizing fine-grained gaze behaviors and providing more targeted enhancements. To inspire gaze-based low vision technology, we investigate the suitable method to collect low vision users’ gaze data via commercial eye trackers and thoroughly explore their challenges in reading based on their gaze behaviors. With an improved calibration interface, we collected the gaze data of 20 low vision participants and 20 sighted controls who performed reading tasks on a computer screen; low vision participants were also asked to read with different screen magnifiers. We found that, with an accessible calibration interface and data collection method, commercial eye trackers can collect gaze data of comparable quality from low vision and sighted people. Our study identified low vision people’s unique gaze patterns during reading, building upon which, we propose design implications for gaze-based low vision technology.

Traumatic injuries require timely intervention, but medical expertise is not always available at the patient’s location. Despite recent advances in telecommunications, surgeons still have limited tools to remotely help inexperienced surgeons. Mixed Reality hints at a future where remote collaborators work side-by-side as if co-located; however, we still do not know how current technology can improve remote surgical collaboration. Through role-playing and iterative-prototyping, we identify collaboration practices used by expert surgeons to aid novice surgeons as well as technical requirements to facilitate these practices. We then introduce ARTEMIS, an AR-VR collaboration system that supports these key practices. Through an observational study with two expert surgeons and five novice surgeons operating on cadavers, we find that ARTEMIS supports remote surgical mentoring of novices through synchronous point, draw, and look affordances and asynchronous video clips. Most participants found that ARTEMIS facilitates collaboration despite existing technology limitations explored in this paper.

The training phases of Deep neural network (DNN) consumes enormous processing time and energy. Compression techniques utilizing the sparsity of DNNs can effectively accelerate the inference phase of DNNs. However, it can be hardly used in the training phase because the training phase involves dense matrix-multiplication using General Purpose Computation on Graphics Processors (GPGPU), which endorse regular and structural data layout. In this paper, we propose the Approximate Random Dropout that replaces the conventional random dropout of neurons and synapses with a regular and online generated patterns to eliminate the unnecessary computation and data access. We develop a SGD-based Search Algorithm that producing the distribution of dropout patterns to compensate the potential accuracy loss. We prove our approach is statistically equivalent to the previous dropout method. Experiments results on multilayer perceptron (MLP) and long short-term memory (LSTM) using well-known benchmarks show that the speedup rate brought by the proposed Approximate Random Dropout ranges from 1.18-2.16 (1.24-1.85) when dropout rate is 0.3-0.7 on MLP (LSTM) with negligible accuracy drop.